© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1448
    Prev
    Next
    INDEX
    Explanations

    shift to or from contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asser
    -0.09
    ously
    -0.09
    IZED
    -0.09
    hips
    -0.09
    utzer
    -0.09
    istrator
    -0.09
    arda
    -0.09
    ÌĨ
    -0.09
     Leer
    -0.09
    ifold
    -0.09
    POSITIVE LOGITS
    ed
    0.18
    (shift
    0.17
    ers
    0.17
     sands
    0.15
    -shift
    0.15
    iness
    0.15
     gears
    0.15
     Shift
    0.15
     shift
    0.14
    edback
    0.14
    Activations Density 0.030%

    No Known Activations